Dust storms in arid and desert areas affect radiation budget,air quality,visibility,enzymatic activities,agricultural products and human health.Due to increased drought and land use changes in recent years,the frequen...Dust storms in arid and desert areas affect radiation budget,air quality,visibility,enzymatic activities,agricultural products and human health.Due to increased drought and land use changes in recent years,the frequency of dust storms occurrence in Iran has been increased.This study aims to identify dust source areas in the Sistan watershed(Iran-Afghanistan borders)-an important regional source for dust storms in southwestern Asia,using remote sensing(RS)and bivariate statistical models.Furthermore,this study determines the relative importance of factors controlling dust emissions using frequency ratio(FR)and weights of evidence(WOE)models and interpretability of predictive models using game theory.For this purpose,we identified 211 dust sources in the study area and generated a dust source distribution map-inventory map-by dust source potential index based on RS data.In addition,spatial maps of topographic factors affecting dust source areas including soil,lithology,slope,Normalized difference vegetation index(NDVI),geomorphology and land use were prepared.The performance of two models(WOE and FR)was evaluated using the area under curve(AUC)of the receiver operating characteristic curve.The results showed that soil,geomorphology and slope exhibited the greatest influence in the dust source areas.The 55.3%(according to FR)and 62.6%(according to WOE)of the total area were classified as high and very high potential dust sources,while both models displayed acceptable accuracy with subsurface levels of 0.704 for FR and 0.751 for WOE,although they predict different fractions of dust potential classes.Based on Shapley additive explanations(SHAP),three factors,i.e.,soil,slope and NDVI have the highest impact on the model's output.Overall,combination of statistic-based predictive models(or data mining models),RS and game theory techniques can provide accurate maps of dust source areas in arid and semi-arid regions,which can be helpful for mitigation of negative effects of dust storms.展开更多
基金The study was financially supported by the Fund for Support of Researchers and Technologists of Iran(97022330)Panhellenic Infrastructure for Atmospheric Composition and Climate Change(PANACEA,MIS 5021516)+1 种基金Competitiveness,Entrepreneurship and Innovation(NSRF 2014-2020)co-financed by Greece and the European Union(European Regional Development Fund).
文摘Dust storms in arid and desert areas affect radiation budget,air quality,visibility,enzymatic activities,agricultural products and human health.Due to increased drought and land use changes in recent years,the frequency of dust storms occurrence in Iran has been increased.This study aims to identify dust source areas in the Sistan watershed(Iran-Afghanistan borders)-an important regional source for dust storms in southwestern Asia,using remote sensing(RS)and bivariate statistical models.Furthermore,this study determines the relative importance of factors controlling dust emissions using frequency ratio(FR)and weights of evidence(WOE)models and interpretability of predictive models using game theory.For this purpose,we identified 211 dust sources in the study area and generated a dust source distribution map-inventory map-by dust source potential index based on RS data.In addition,spatial maps of topographic factors affecting dust source areas including soil,lithology,slope,Normalized difference vegetation index(NDVI),geomorphology and land use were prepared.The performance of two models(WOE and FR)was evaluated using the area under curve(AUC)of the receiver operating characteristic curve.The results showed that soil,geomorphology and slope exhibited the greatest influence in the dust source areas.The 55.3%(according to FR)and 62.6%(according to WOE)of the total area were classified as high and very high potential dust sources,while both models displayed acceptable accuracy with subsurface levels of 0.704 for FR and 0.751 for WOE,although they predict different fractions of dust potential classes.Based on Shapley additive explanations(SHAP),three factors,i.e.,soil,slope and NDVI have the highest impact on the model's output.Overall,combination of statistic-based predictive models(or data mining models),RS and game theory techniques can provide accurate maps of dust source areas in arid and semi-arid regions,which can be helpful for mitigation of negative effects of dust storms.
